Search for: All records

Abstract MotivationHigh-throughput sequencing (HTS) is a modern sequencing technology used to profile microbiomes by sequencing thousands of short genomic fragments from the microorganisms within a given sample. This technology presents a unique opportunity for artificial intelligence to comprehend the underlying functional relationships of microbial communities. However, due to the unstructured nature of HTS data, nearly all computational models are limited to processing DNA sequences individually. This limitation causes them to miss out on key interactions between microorganisms, significantly hindering our understanding of how these interactions influence the microbial communities as a whole. Furthermore, most computational methods rely on post-processing of samples which could inadvertently introduce unintentional protocol-specific bias. ResultsAddressing these concerns, we present SetBERT, a robust pre-training methodology for creating generalized deep learning models for processing HTS data to produce contextualized embeddings and be fine-tuned for downstream tasks with explainable predictions. By leveraging sequence interactions, we show that SetBERT significantly outperforms other models in taxonomic classification with genus-level classification accuracy of 95%. Furthermore, we demonstrate that SetBERT is able to accurately explain its predictions autonomously by confirming the biological-relevance of taxa identified by the model. Availability and implementationAll source code is available at https://github.com/DLii-Research/setbert. SetBERT may be used through the q2-deepdna QIIME 2 plugin whose source code is available at https://github.com/DLii-Research/q2-deepdna. 

Abstract Knowledge of how habitat restoration shapes soil microbial communities often is limited despite their critical roles in ecosystem function. Soil community diversity and composition change after restoration, but the trajectory of these successional changes may be influenced by disturbances imposed for habitat management. We studied soil bacterial communities in a restored tallgrass prairie chronosequence for >6 years to document how diversity and composition changed with age, management through fire, and grazing by reintroduced bison, and in comparison to pre-restoration agricultural fields and remnant prairies. Soil C:N increased with restoration age and bison, and soil pH first increased and then declined with age, although bison weakened this pattern. Bacterial richness and diversity followed a similar hump-shaped pattern as soil pH, such that the oldest restorations approached the low diversity of remnant prairies. β-diversity patterns indicated that composition in older restorations with bison resembled bison-free sites, but over time they became more distinct. In contrast, younger restorations with bison maintained unique compositions throughout the study, suggesting bison disturbances may cause a different successional trajectory. We used a novel random forest approach to identify taxa that indicate these differences, finding that they were frequently associated with bacteria that respond to grazing in other grasslands. 

The booklet provides description and results of the International Workshop on Biology and Biotechnology of Thermophilic Microorganisms held in Georgia and Armenia in October of 2015.